Intelligent computing hybrid models on estimating the consolidation settlement of shallow foundations

The settlement of shallow foundations is one of the predominant topics in geotechnical engineering due to the nonlinear behaviour of the soil. This study emphasizes the assessment of evolutionary hybrid models for predicting the primary consolidation settlement of shallow foundations. To achieve this, the Load (P), Void ratio (e₀), Compression index (C_c), and dry density (γ) were considered for estimating the primary consolidation settlement of the shallow foundation. In this research, the Artificial Neural Network (ANN)-based hybrid models such as Imperialist Competitive Algorithm (ICA), Ant Colony Optimization (ACO), Ant Lion Optimization (ALO), and Teaching Learning Optimization (TLO) were utilized for the determination of primary consolidation settlement of shallow foundations. A total of 500 datasets were adopted for this purpose and segregated to 350 data for training and the remaining for validation. The ANN–ICA model was found to be the best model with higher precision (R = 0.981) and the least root-mean-square error (RMSE = 0.056). To validate the potential of the developed intelligent models, various statistical metrics and figures were utilized.